How do we turn words into vectors? My Patreon : www.patreon.co...
Пікірлер: 77
@matthewson89173 жыл бұрын
Finally, someone made a clear and concise introduction for Word2Vec! I admire you!
@revathik92258 ай бұрын
Great video. One thing to add: instead of always discarding the context vectors at the end, another strategy (mentioned in other videos/articles) is to concatenate or add the two vectors for a word.
@hahahaYL-h3x6 ай бұрын
You are a genius! You are able to explain abstract things well with only white board (no animation!)
@a009549263 жыл бұрын
This is amazing!! I remember trying to understand this back when it was first published, and i failed so hard...thank you
@yangwang96883 жыл бұрын
Great explanation, it’s pure gold! Can you make a video in terms of hierarchical softmax? It confuses me for a long time.
@DC-tq1kh7 ай бұрын
Probably the best video explanation I watched. thank you.
@DennisRice-lh3nd Жыл бұрын
The best and most concise explanation of Word2Vec that I've seen so far. I probably need to go back and review gradient descent again, because updating the weights is still confusing.
@jett_royce3 жыл бұрын
Great video. You mentioned that we discard the context vectors and take the main vectors as our final word embeddings. I just want to add that based on the literature, you can also add the main and context vectors, or concatenate them.
@sefinehtesfa51892 жыл бұрын
I appreciate your explanations. I was stuck on Word2Vec. However, you explainde this more than enough. Thank you so much!!!
@drsandeepvm56222 жыл бұрын
Exceptionally simplified explanation. Thanks 😊
@vctorroferz3 ай бұрын
Incredible and amazing explanation! Thanks so much for such great content!
@ritvikmath3 ай бұрын
Glad you liked it!
@purpleearth6 ай бұрын
This is a superb explanation
@SonalGore-q1v7 ай бұрын
Cool....Made it very easy for me to understand about word2vec. Great explanation !!
@ritvikmath7 ай бұрын
Glad it helped!
@bharathtvadhoola7152 жыл бұрын
Awesome video! numerical example was particularly helpful. Cheers :)
@nobodyelse22302 жыл бұрын
You're so good! Thank you very much for this explanation, my minds are so slear after it, magic!
@saikatroy38183 жыл бұрын
Explained in lucid manner. Nice video.
@austossen3 жыл бұрын
this is by far the best explanation of word2vec on youtube over any university lecture but one question. where and how are you getting your initial vector values in this example for V(like) and V(data)? can you also clarify the components of the vector? you have two columns/elements for each vector in the main vector and context vector.
@tellyrotsyourbrain2 жыл бұрын
Exactly what I was wondering. Where do the initialisations of these vectors come from? I'm guessing they're initialised randomly, with the algorithm evolving the distribution into something that relates to the training data.
@Recoils14 Жыл бұрын
This explanation is so well done! Thank you!
@ritvikmath Жыл бұрын
Glad it was helpful!
@utuber1752 Жыл бұрын
EXCELLENT explanation!
@junekang23648 ай бұрын
Great video! Thank you for explaining this so clear.
@ebujak1 Жыл бұрын
Great Word2Vec video. Nice touch with blue for Main and red for Context. Working an example with numbers is also very good. Can we please have a follow up video (from ritvik "from the future" :) ) to do the UPDATE part of the loop? We know there are multiple ways to do this UPDATE, but just expound on the "simple" method of moving the vectors as you illustrated in 2D. Thanks.
@testimonies29143 жыл бұрын
Nice ...thannk you so much
@harshalingutla73182 жыл бұрын
Brilliant explanation. To the point.
@MikeKittelberger9 ай бұрын
Awesome explanation, you safe me a lot of time. Thank you! :)
@dominicprior9844 Жыл бұрын
Wow, such a nice clear video! Many thanks!
@michaelm358 Жыл бұрын
Outsanding!
@FullStackAmigo Жыл бұрын
I learned something, thanks a lot!
@hameddadgour2 жыл бұрын
Great presentation!
@muhammadal-qurishi71103 жыл бұрын
You are always great in your explanations Can you explain CRF please
@pampagrimaldi8584 Жыл бұрын
great explanation! thank you!
@ritvikmath Жыл бұрын
Glad it was helpful!
@Halo-uz9nd3 жыл бұрын
Another fantastic video! The main/context embeddings kind of confused me but the ending really cleared it up. Curious to know if there is a deliberate way of choosing # of dimensions or if its simply trial and error. On a side note, will you be participating in the "66 days of data" challenge this July?
@kostjamarschke46132 жыл бұрын
Phenomenal stuff!
@kostjamarschke46132 жыл бұрын
Honestly phenomenal. You covered 80% of a 90-minute Masters-level ML lecture in 13 minutes and made it very easy to understand.
@edphi Жыл бұрын
Very awesome
@HiteshKumar-bk2od3 жыл бұрын
Can you please make a video on transformers, attention and Bert models in detail . It will be in Continuation with word vectors.
@zhiyili67072 жыл бұрын
Thank you for the video! Great content!
@gnkk60022 жыл бұрын
Good job as always👏
@vincentouwendijk37466 ай бұрын
Great video!
@ritvikmath6 ай бұрын
Glad you enjoyed it
@houyao21473 жыл бұрын
very intuitive!
@sa-vx5vi Жыл бұрын
Thanks a lot
@arshadkazi45592 жыл бұрын
Could you elaborate more on context and main embedding please? 6:00
@mmenjic2 жыл бұрын
And how do we distinguish between 2 same words in this case "data" if we have larger text where data is next to science but it is also close to other word or words for example data processing, data mining, data validation, data.... data..... everything, is it the case that word data is "closer" to word science in general than it is to word processing or there is some other mechanism for this ?
@VincentVanZgegh Жыл бұрын
Great video ! Thx
@ritvikmath Жыл бұрын
Glad you liked it!
@gabrielemoro3045 ай бұрын
the dot product between V_like and V_data should be 0.4 and not 0.6 right? (min 8:27)
@KD4wg4 ай бұрын
yes, the dot product is 0.4. But our score is the sigmoid of the dot product. And sigmoid(0.4) is roughly 0.598 ^^
@0815-j3s5 ай бұрын
Simply since the distances are invariant under orthogonal transformations of the space "embeddings" (by the way: Not in the mathematical sense) are not unique. But they also depend on the prupose of the model.
@lsacy83472 жыл бұрын
why is this word2vec so different from "conventional" word2vec where you use a neural network and bag of words to calculate the weights matrix? ok, my bad, just realized you talked about neural network update method towards the end.
@oraz.2 жыл бұрын
What determines the dimension of the word vectors? Edit I guess it's just an engineering decision.
@nobodyelse22302 жыл бұрын
Hello again! After a couple of days of studying another materials, I realized that I don't understand where the formulas for the score and the error come from, I don't see them in the books I read (and I haven't seen this approach with labels yet either). Are there any papers or books where I can find them and the prove that they work?
@jagadeeshwaran15124 ай бұрын
How does the Main embedding is calculated?. How is the vector defined?
@kevinscaria Жыл бұрын
Wow
@robertc63433 жыл бұрын
So how does it happen than king - man + woman = queen, a very common selling example of wod2vec?
@muhammadal-qurishi71103 жыл бұрын
check this video and you will have clear understanding kzbin.info/www/bejne/al60oICaiNZ6las
@robertc63433 жыл бұрын
@@muhammadal-qurishi7110 cool 👍🏻 thanks!
@golnoushghiasi76982 жыл бұрын
Can you explain some more NLP models such as Bert, Fasttext and transformers?
@bartoszko4028 Жыл бұрын
Well explained, but doesn't sigmoid function give values from 0 to 1? Then maybe it should be tanh activation function?
@ebujak1 Жыл бұрын
Score needs to be positive since the error needs to be opposite (error = label - score). tanh is negative and positive ... so hard to interpret error.
@agamchug5952 жыл бұрын
How is the initial size of the vectors determined? As you mentioned that traditionally there may be vectors with 50 dimensions and your example has used 2 to ease understanding.
@priyasah61238 ай бұрын
How to calculate score ? We need to take dot product of what exactly with main and context ?
@vyvu4436 ай бұрын
Ritvik... can you do NLP, word embeddings with GloVe and FastText :D :D :D Thank you in advance!
@kundansaha48772 жыл бұрын
please make a video how spacy works
@CarlJohnson-jj9ic Жыл бұрын
Is chloroform FDA approved for a mechanics lean on a judgement?
@bilalsidiqi99922 жыл бұрын
Could you please implement some NLP models in pytorch or tensorflow?
@moatasem444 Жыл бұрын
There is a prepared embedding?
@sachinrathi78142 жыл бұрын
Can someone will explain where those 2 numeric values (vector representation) for like word, -.2 and -1 comes from ? Word2vec is used to create numeric representation of words in vector form or create vector in such a way that word which are close in documents are also close in vectors representation as well ?
@goumuk2 жыл бұрын
initially the values are randomly set. after each iteration of computation, the values keep getting updated.
@RonLWilson2 жыл бұрын
Just FYI, I just made and uploaded a KZbin video where I used bits of your video here as a use case to illustrate a graphical ontology language that I am calling UniML, Universal Modeling L (not to be confused with UML, Unified modeling Language). While things like neural nets map transformation or functions (f: X -> Y) UniML attempts to model more than that and model the thing itself, including any such transformations as an ontology model but not using just symbols such as does ontology languages such as OWL or RDF but graphically so that graphically depicts the under lying data structures. Here is a link to my video kzbin.info/www/bejne/mJrSq2Voa6iWjbs
@gagangayari59812 жыл бұрын
Perfect explanation. How would doc2vec fit along the same lines with the algorithm you mentioned ? Can you please briefly tell ? @ritvikmath